Nguyen Nang Hung Van

Nguyen Nang Hung Van

Auto-generated profile, based on publicly available information

Nguyen Nang Hung Van

The University of Danang - University of Science and Technology

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 August 2025 in IEEE Transactions on Learning Technologies
Verified
Journal Article
Closed access
NVNguyen Nang Hung Van
Nguyen Nang Hung Van
DHDo Phuc Hao
Do Phuc Hao
VHVan Nam Hoang
Van Nam Hoang
TNTruc Thi Kim Nguyen
Truc Thi Kim Nguyen
MPMinh Tuan Pham
Minh Tuan Pham
This study investigates how technical advances in LLMs translate into measurable educational benefit. University admission counseling plays a crucial role in helping prospective students make their higher education decisions. However, traditional advisory methods are constrained by issues such as limited scalability, personalization, and the ability to handle large volumes of inquiries. With the growing need for real-time assistance, Artificial Intelligence (AI), particularly Large Language Models (LLMs), presents a promising solution to these challenges. This paper introduces an AI-driven university admission counseling system that automates routine inquiries, personalizes guidance, and improves accessibility. We develop a formal mathematical framework to represent the counseling task, using embedded and similarity metrics to assess the compatibility of student profiles with academic programs. The system incorporates a multistage workflow for efficient data processing, embedded generation, and AI-driven recommendation. We evaluated the performance of several LLMs eLLAMA, eGPT, and eDEEPSEEK through retrieval-augmented generation (RAG), measuring output quality with NLP metrics such as BLEU, ROUGE, METEOR, and BERTScore. Our results demonstrate that LLMs can significantly improve the efficiency and quality of admission counseling, providing a scalable and adaptable solution that demonstrably enhances student confidence and decision quality.

20 October 2020 in Information and Control Systems
Verified
Journal Article
Open access
PDF file
NNNang Hung Van Nguyen
Nang Hung Van Nguyen
MPMinh Tuan Pham
Minh Tuan Pham
DHDo Phuc Hao
Do Phuc Hao
CPCong Thang Pham
Cong Thang Pham
KTKanta Tachibana
Kanta Tachibana
Постановка проблемы: глубокое обучение играет важную роль в машинном обучении и искусственном интеллекте. Оно находит широкое применение во многих областях, где приходится оперировать большими массивами данных, например в обработке естественных языков или распознавании изображений. Высокая размерность данных ведет к таким проблемам машинного об- учения, как чрезмерное обучение или падение точности. Для их преодоления предлагаются методы одновременного снижения размерности данных и вычислительной сложности. Недостаток этих методов состоит в их ориентированности на данные, распределенные по плоскости. В случае данных, распределенных по гиперсфере, таких как передвигающийся в пространстве объект, результаты обработки показывают качество ниже ожидаемого. Цель: применение конформной геометрической алгебры для одновременного снижения размерности массива данных, необходимых для выделения признаков и распознавания действий человека с использованием рекуррентной нейронной сети. Результаты: данные о действиях человека в трехмерной системе координат подвергаются предобработке и нормализации путем вычисления отклонений от средних координат. Далее данные преобразуются в векторы в пространстве конформной геометрической алгебры, а их размерность снижается для извлечения векторов признаков. Наконец, применяется модель рекуррентной нейронной сети для обучения векторов признаков. Опытные результаты, полученные на массиве данных захвата движений для восьми действий, показали, что комбинация конформной геометрической алгебры с рекуррентной нейронной сетью обеспечивает наилучший результат в 92,5 % случаев. Практическая значимость: некоторые действия человека, например прыжок или танец, не сопряжены с перемещением в пространстве, в отличие от таких, как бег или ходьба. Поэтому необходим способ стандартизации действий. В случае данных, распределенных по гиперсфере, разработанный метод позволяет выделять признаки с одновременным снижением размерности массива данных для распознавания действий человека посредством рекуррентной нейронной сети.

30 October 2025 in Biomedical Signal Processing and Control
Verified
Journal Article
Closed access
NVNguyen Nang Hung Van
Nguyen Nang Hung Van
DHDo Phuc Hao
Do Phuc Hao
VHVan Nam Hoang
Van Nam Hoang
TNTruc Thi Kim Nguyen
Truc Thi Kim Nguyen
Tran Duc LeTran Duc Le
Tran Duc Le

7 December 2023
Verified
Conference Paper
Open access
NVNguyen Nang Hung Van
Nguyen Nang Hung Van
DHDo Phuc Hao
Do Phuc Hao
VHVan Nam Hoang
Van Nam Hoang
ABAleksandr Borodko
Aleksandr Borodko
Tran Duc LeTran Duc Le
Tran Duc Le
Human Action Recognition (HAR) has emerged as a pivotal challenge in the rapidly evolving realm of artificial intelligence and computer vision. This research delves into enhancing action recognition in video sequences by synergizing the Fast Fourier Transform (FFT) capabilities and the EfficientNet model. We employed the UCF101 dataset, encompassing a diverse range of action categories, to validate our approach empirically. The results underscored that incorporating FFT in the preprocessing stage amplifies the recognition efficacy of the EfficientNet model. Comparative analyses further substantiated the superiority of this combined approach over conventional methods, marking a significant contribution in the domain of action video recognition.

30 September 2025 in The University of Danang - Journal of Science and Technology
Verified
Journal Article
Open access
PDF file
TNTruc Thi Kim Nguyen
Truc Thi Kim Nguyen
VHVan Nam Hoang
Van Nam Hoang
PTPham Ngoc Tinh
Pham Ngoc Tinh
NVNguyen Nang Hung Van
Nguyen Nang Hung Van
This paper presents an Artificial Intelligence–driven chatbot for university admission consultation using Large Language Models (LLMs). The system integrates semantic retrieval with Retrieval-Augmented Generation (RAG) and employs a hybrid strategy that combines vector similarity and keyword matching to provide accurate and context-aware answers. The chatbot was trained on admission FAQs, official documents, and consultation records from Dong A University, ensuring relevance to real user needs. Implementation leverages efficient prompt construction and memory management to support interactive and personalized responses. Experimental results show improved retrieval precision and practical benefits in reducing staff workload and offering consistent support to prospective students. Current limitations include the use of a single-university dataset and a technical evaluation focused on retrieval metrics. Future work will expand to multi-institution data, user studies, and multilingual or voice-enabled interaction to enhance generalizability and real-world impact.

18 July 2023 in Các công trình nghiên cứu, phát triển và ứng dụng Công nghệ Thông tin và Truyền thông
Verified
Journal Article
Closed access
VPVan Quan Pham
Van Quan Pham
NNNăng Hùng Vân Nguyễn
Năng Hùng Vân Nguyễn
N this era of advanced technology, the interconnection of various devices has become a crucial aspect. As a solution to optimize this interconnectivity, the Internet of Things has emerged as a prominent solution. However, ensuring the security of Internet of Things systems is equally essential. Timely detection of potential attacks on Internet of Things systems can effectively mitigaterisks and minimize damages. In the present research, we investigated the efficacyof four algorithms, namely Decision Tree, K Nearest Neighbors , Random Forest, and Extreme Gradient Boosting , in detecting and classifying Internet of Thingsbotnets. Our findings demonstrate that all four algorithms exhibit remarkable effectiveness in detecting and classifying botnets. Among these algorithms, the Extreme Gradient Boosting algorithm achieved the highest accuracy, while the Decision Tree algorithm exhibited the shortest execution time. This study highlightsthe potential of machine learning algorithms in detecting and reducing securitythreats in Internet of Things devices. By leveraging these algorithms, it is possible to detect and classify botnets promptly, thus minimizing the risk of securitybreaches in Internet of Things systems.